Exploring responsible innovation with privacy preservation: federated learning policies for digital finance services in Asia

Advancements in artificial intelligence (AI) and financial technologies (fintech) are transforming digital finance with innovations in personalized products, fraud detection, accessibility and risk management. However, these innovations require sensitive customer data, raising privacy and security concerns. Federated learning (FL) offers a solution by enabling institutions to train AI models locally, sharing only model updates and minimizing data-sharing risks. This paper contains an exploration of how FL can advance AI-driven innovation while ensuring privacy compliance, in particular in Asia, by analysing FL key use cases, including personalized recommendations, fraud detection and credit scoring. We then propose frameworks for FL platform assessments and stakeholder analysis for policy recommendations to enhance data security, regulatory compliance and ethical guidelines for responsible innovation in digital finance.